The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 01, 2025

Filed:

Oct. 30, 2020
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Nishanth Chandran, Bangalore, IN;

Divya Gupta, Bangalore, IN;

Aseem Rastogi, Bangalore, IN;

Rahul Sharma, Bangalore, IN;

Nishant Kumar, Ranchi, IN;

Mayank Rathee, Panchkula, IN;

Deevashwer Rathee, Panchkula, IN;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 5/04 (2023.01); G06N 3/08 (2023.01); H04L 9/34 (2006.01);
U.S. Cl.
CPC ...
G06N 5/04 (2013.01); G06N 3/08 (2013.01); H04L 9/34 (2013.01); H04L 2209/46 (2013.01); H04L 2209/50 (2013.01);
Abstract

A secure inference over Deep Neural Networks (DNNs) using secure two-party computation to perform privacy-preserving machine learning. The secure inference uses a particular type of comparison that can be used as a building block for various layers in the DNN including, for example, ReLU activations and divisions. The comparison securely computes a Boolean share of a bit representing whether input value x is less than input value y, where x is held by a user of the DNN, and where y is held by a provider of the DNN. Each party computing system parses their input into leaf strings of multiple bits. This is much more efficient than if the leaf strings were individual bits. Accordingly, the secure inference described herein is more readily adapted for using in complex DNNs.


Find Patent Forward Citations

Loading…